Abdominal Multi-Organ Segmentation Based on Feature Pyramid Network and Spatial Recurrent Neural Network

TL;DR

This paper introduces a novel ultrasound image segmentation model combining Feature Pyramid Network and Spatial Recurrent Neural Network to improve accuracy and robustness by leveraging multi-scale features and spatial relationships.

Contribution

The paper proposes a new segmentation model that integrates FPN and SRNN, specifically designed to handle scale variations and spatial context in abdominal ultrasound images.

Findings

Enhanced segmentation accuracy demonstrated on ultrasound datasets

Effective modeling of spatial relationships improves robustness

Combines multi-scale feature extraction with spatial context analysis

Abstract

As recent advances in AI are causing the decline of conventional diagnostic methods, the realization of end-to-end diagnosis is fast approaching. Ultrasound image segmentation is an important step in the diagnostic process. An accurate and robust segmentation model accelerates the process and reduces the burden of sonographers. In contrast to previous research, we take two inherent features of ultrasound images into consideration: (1) different organs and tissues vary in spatial sizes, (2) the anatomical structures inside human body form a relatively constant spatial relationship. Based on those two ideas, we propose a new image segmentation model combining Feature Pyramid Network (FPN) and Spatial Recurrent Neural Network (SRNN). We discuss why we use FPN to extract anatomical structures of different scales and how SRNN is implemented to extract the spatial context features in abdominal ultrasound images.